EP2141658A1 - Verfahren zur Erkennung von Layoutbereichen in einem Videobild und Verfahren zur Erzeugung eine Bildes reduzierter Grösse welches das Erkennungsverfahren verwendet - Google Patents

Verfahren zur Erkennung von Layoutbereichen in einem Videobild und Verfahren zur Erzeugung eine Bildes reduzierter Grösse welches das Erkennungsverfahren verwendet Download PDF

Info

Publication number
EP2141658A1
EP2141658A1 EP09164076A EP09164076A EP2141658A1 EP 2141658 A1 EP2141658 A1 EP 2141658A1 EP 09164076 A EP09164076 A EP 09164076A EP 09164076 A EP09164076 A EP 09164076A EP 2141658 A1 EP2141658 A1 EP 2141658A1
Authority
EP
European Patent Office
Prior art keywords
areas
area
salience
maximum
saliency map
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP09164076A
Other languages
English (en)
French (fr)
Other versions
EP2141658B1 (de
Inventor
Christel Chamaret
Olivier Le Meur
Jean-Claude Chevet
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
THOMSON LICENSING
Original Assignee
Thomson Licensing SAS
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Thomson Licensing SAS filed Critical Thomson Licensing SAS
Publication of EP2141658A1 publication Critical patent/EP2141658A1/de
Application granted granted Critical
Publication of EP2141658B1 publication Critical patent/EP2141658B1/de
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/04—Context-preserving transformations, e.g. by using an importance map
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
    • G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20164—Salient point detection; Corner detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/09—Recognition of logos

Definitions

  • This invention relates to the detection of layout areas, such as logos and/or scores, in a video image and the generation of a reduced size image from a source image.
  • a third known technique consists in comparing visual content in the image to be processed with a predefined layout base.
  • the visual content of image areas is compared with the visual content of each of the layouts contained in the base.
  • a layout is detected when the visual content is identical to the visual content of the area tested. This technique only detects layouts contained in the base and thus involves prior knowledge of logos to be detected.
  • the purpose of the present invention is to propose a solution to overcome all or some of the disadvantages previously cited.
  • the detection of layout in a source image is carried out from a saliency map of said source image said saliency map being generated from a visual attention model.
  • the present invention proposes a method for automatic detection in a source image of at least one area referred to as a layout area comprising at least one layout, such as a logo and/or a score, comprising the following steps:
  • the detection is thus carried out from a single source image and does not require prior knowledge of the layouts to be detected.
  • the step of determining a layout area in a source image comprises the following steps:
  • the search area comprises at least one area of predefined size in the saliency map corresponding to a source image area in a corner of the source image.
  • said at least one search area comprises m areas of predefined size of the saliency map each corresponding to a area of the source image located in a corner of the source image, m being comprised between 2 and 4.
  • step a) of the method comprises the following steps:
  • the two search areas are advantageously the areas of the saliency map corresponding to two bands of predefined width of the upper and lower parts of the source image and at least three maximum salience points are searched for in these two search areas.
  • the maximum salience area defined for a maximum salience point is advantageously a circle, of a predefined radius, centred on said maximum salience point.
  • the invention also relates to a method for processing a source image, able to generate a reduced size image from said source image, comprising the following steps:
  • the points contained in the bounding window(s) determined by the automatic layout detection method are set to zero in the saliency map used to generate the reduced size image.
  • the source image layout areas which are not areas of interest for the viewer, do not interfere with the determination the reduced image.
  • the reduced size image is generated in such a way that it does not contain pixels corresponding to points contained in the bounding window(s) determined by the layout area automatic detection method.
  • the source image layout areas are determined from the saliency map of this image.
  • a layout is detected when two maximum salience areas are detected in a same region of the saliency map, the first maximum salience area corresponding to the start of the layout and the second maximum salience area corresponding to the end of the layout.
  • a layout designates any information added or embedded into the source image such as a logo, information on duration or time, a score in the case of images relating to a sports event.
  • Figure 1 shows the steps from the first embodiment according to the invention.
  • the source image to be processed is an image taken from a football match. It shows a football player next to a football.
  • the match score is displayed in the upper left-hand side of the image and an AF1 logo identifying the television channel retransmitting the football match is displayed in the upper right-hand side.
  • a saliency map of the source image is generated using a visual attention model.
  • the generation of a saliency map is described in the European patent EP 1 685 288 .
  • This saliency map associates with each pixel of the source image a salience value which is a function of the perceptual interest of the image pixel.. The higher the perceptual interest of the image pixel, the higher the salience value.
  • Salience values are for example normalized and comprised between 0 and 255.
  • the salience value is represented in the saliency map by a point having the same spatial coordinates as the source image pixel that it characterizes and a level of grey proportional to the salience value of the pixel.
  • the lightest points on the saliency map representing the most salient points of the source image correspond to areas of strong contrast in the image.
  • the lightest points are found in the image areas representing the player, the ball, the match score and the logo.
  • step S2 are sought, in at least one predefined area of the saliency map called the search area, two points having a salience value equal to or almost equal to the maximum salience value of the saliency map and distant by at least p. These two points are called maximum salience points in the remainder of the description. If the search is performed in several search areas, two maximum salience points are searched for in each of these areas. In a saliency map with normalized values between 0 and 255, two points are searched for at a distance of at least p points, and having a salience value equal to 255, or, failing this, close to 255, preferably comprised between 250 and 255.
  • the number p may vary according to the size of the source image. It is for example at 25in the case of a 360x240 pixels image or a 352x288 pixels image.
  • the search areas are advantageously areas of predefined size of the saliency map corresponding to areas located in the corners of the source image, areas in which a layout is likely to be present.
  • the search areas are areas of the saliency map corresponding to two rectangular areas located respectively in the left-hand and right-hand corners of the source image.
  • the search is carried out in the areas of the saliency map corresponding to the four corners of the source image.
  • each search area the search is for example carried out by scanning the area, from left to right and from top to bottom.
  • the search area is scanned a first time to ascertain the maximum salience value of this area. This value must be equal to or close to 255 to correspond to the start or end of the layout area. It is preferably greater than 250. In the absence of such a value, no layout area will be detected in this search area and, if necessary, the next search area should then be considered. If a salience value close to 255 is found, a second scan is then carried out to search for the point or points of the search area having a maximum salience value. Each time such a point is detected, it is selected and the points around the selected points are inhibited.
  • the points belonging to the circle of radius R centred on the selected point are inhibited for example R being equal to p points.
  • the scanning continues ignoring the inhibited points and selecting in the same way, the other points of the saliency map having the maximum salience value. If two points were not selected following this scan, the maximum salience value is decremented and further scans are carried out until two maximum salience points are selected. Scans are discontinued if, after a decrementation the maximum salience value becomes less than 250. If two points have not been selected, the following search area is then considered.
  • a maximum salience area is then defined around each of the two selected points.
  • this area corresponds to the inhibited area previously defined, that is to say a circle of radius R centred on the selected point.
  • the salience values of the points located outside of the defined maximum salience areas are set to zero.
  • a window bounding the two maximum salience areas is defined in each search area comprising two maximum salience areas. If x and y designate horizontal and vertical axes respectively in the saliency map, this window is preferably the smallest rectangle having two sides parallel to the x axis and two sides parallel to the y axis and bounding the two areas selected.
  • the source image pixels, for which corresponding points in the saliency map belong to this bounding window, are thus considered according to the invention, as belonging to a layout area in the source image.
  • FIG. 2 shows the steps of the second embodiment according to the invention.
  • the source image to be processed is a geographical map of the South of France.
  • a saliency map of the image is generated using a visual attention model as described in step S 1 of the first embodiment.
  • the most salient points of the saliency map are the areas corresponding to the logo, to the text contained within the image and to the borders between the different colour zones of the geographical map.
  • step S2' three maximum salience areas are searched for in two predefined search areas of the saliency map.
  • the search is carried out in two bands of predefined width from the saliency map, one located in the upper part of the saliency map and the other in the lower part.
  • this search is, for example, carried out by scanning the two bands of the saliency map, from left to right and top to bottom. The two bands are first scanned to obtain the maximum salience value of the two bands. This value must be equal to 255 or if not, close to 255, for example comprised between 250 and 255. In the absence of such a value, no layout area will be detected.
  • the two bands are then scanned for a second time to search for the point or points having a maximum salience value. Each time such a point is detected, it is selected and the points around the selected points are inhibited. For example, the points belonging to the circle of radius R centred on the selected point are inhibited. The scanning of the two bands continues ignoring the inhibited points and, if present two other points on the saliency map having the maximum salience value are selected. If three points are not selected following this scan, the maximum salience value is decremented and other scans are carried out until the selection of three maximum salience points is obtained.
  • a maximum salience area is then defined around each of the three selected points.
  • this area corresponds to the previously defined inhibited area, that is to say to the circle of radius R centred on the selected point.
  • the salience values of the points located outside of the defined maximum salience areas are set to zero.
  • one of the maximum salience areas is located in the upper band of the saliency map and the two other maximum salience areas are located in the lower band of the map.
  • step S'3 one of the three maximum salience areas is eliminated.
  • the purpose of this step is to conserve the two maximum salience areas likely to coincide with the beginning and end of a layout, the third area is generally a false alarm.
  • the three maximum salience points are classed from the most salient to the least salient.
  • a first pair of points formed by the two most salient points is then tested verifying if this pair fulfils one or more predefined criteria. If this pair fulfils these criteria, the maximum salience areas corresponding to these two points are conserved and the maximum salience area corresponding to the least salient point is eliminated. Otherwise, a second pair made up of the most salient and the least salient of the three points is tested, then, if necessary, a third pair made up of the two least salient points is tested.
  • FIG. 3 shows a saliency map in which three maximum salience points P1, P2 and P3 have been identified.
  • the maximum salience areas of radius R relating to these three points are labelled as Z1, Z2 and Z3.
  • Points P1 and P2 are present in a band B1 in the upper part of the saliency map and point P3 is present in a band B2 in the lower part of the saliency map.
  • Bands B1 and B2 represent search areas.
  • R1 designates the smallest rectangle having two sides parallel to the x axis and two parallel to the y axis and bounding areas Z1 and Z2.
  • R2 designates the smallest rectangle having two sides parallel to the x axis and two sides parallel to the y axis and bounding areas Z1 and Z3 and R3 designates the smallest rectangle having two sides parallel to the x axis and two sides parallel to the y axis and bounding areas Z2 and Z3.
  • C designates the centre of the saliency map which corresponds to the centre of the source image.
  • a first criterion is satisfied by a pair of points when the height (dimension according to the y axis) of the rectangle bounding the two maximum salience areas of the points of the pair under consideration is less than a predefined maximum height. This criterion ensures a guarantee that these two maximum salience areas come from the same upper or lower saliency map band. This criterion is always satisfied by the maximum salience areas representing the beginning and end of a layout.
  • a second criterion is satisfied by a pair of points when the surface area of the rectangle bounding the two maximum salience areas of the points of the pair under consideration is less than a predefined maximum surface area. This criterion enables a guarantee that the two points under consideration are noticeably aligned vertically or horizontally.
  • a third criterion is satisfied by a pair of points when, for each point of the pair, the distance between this point and the centre C of the saliency map is greater than a minimum distance.
  • the question of whether the three point pairs fulfil the first criterion is verified. Pairs that do not fulfil this first criterion are eliminated. If one pair fulfils this first criterion, it is selected. Otherwise, the pairs that were not eliminated are tested to see if they fulfil the second criterion. If one pair fulfils this second criterion, it is selected. Pairs that do not fulfil these first two criteria are eliminated. Finally if several pairs remain, those that are not eliminated are checked to see if they satisfy the third criterion. If one pair fulfils this third criterion, it is selected. It is possible to use only the first criterion or only the first two criteria. It is also possible to provide for other criteria if 3 are not enough to select only two of the three maximum salience areas.
  • the window bounding the two selected maximum salience areas is determined in the saliency map.
  • This window is preferably the smallest rectangle having two sides parallel to the x axis and two sides parallel to the y axis and bounding both selected areas.
  • the source image pixels for which the corresponding points in the saliency map belong to this bounding window are thus considered, according to the invention as belonging to a layout area in the source image.
  • q maximum salience points are sought and q maximum salience areas are defined at step S'2, q being greater than 3.
  • This number of maximum salience areas is then limited to 2 by applying the predefined criteria to all the areas area pairs possible.
  • the number n of search areas may be increased, the number q of maximum salience areas defined being then at least equal to n+1.
  • the automatic layout area detection method comprises a binarisation step for the saliency map before determining the bounding window (step S4 or S'3).
  • the salience value of points in the three maximum salience areas (first embodiment) or of the two maximum salience areas of each search area (second embodiment) is set to 255 (or to the maximum salience value) and the salience value of the other points is set to zero.
  • This purpose of this binarisation step is to facilitate the bounding window determination step.
  • the automatic layout area detection method comprises a step for checking temporal consistency of the maximum salience areas defined in step S4 or S'3.
  • This step consists in verifying, for each point of the maximum salience area, if it belongs to such an area in the preceding image or images.
  • This step can be implemented using counters. A counter is provided for each search area point for example. The counter is incremented each time that the point considered belongs to a maximum salience area in a given image. Thus, if the point under consideration belongs to a maximum salience area in the current image belonging also to a maximum salience area in the preceding image(s), this point is maintained as being part of a maximum salience area.
  • the purpose of this step is to reinforce the choice of maximum salience areas defined in the current image.
  • the invention also relates to an image processing method able to generate a predefined reduced size image, from a source image, intended to be displayed on a reduced size screen.
  • An automatic reframing method is also discussed.
  • Such a method traditionally comprises a step of generation of a source image saliency map and a step of generation of a reduced size image from a source image using the saliency map.
  • the reduced size image generated being the sub-image or part of the source image with the most perceptual interest for the viewer.
  • the reduced size image generation step comprises more specifically defining, in a source image a framing window, which is smaller than the source image containing the most salient points of the image or the greatest number of salient points.
  • the reduced size image generated is thus the image contained in the framing window.
  • the layout areas present a problem in determining the size and position of the framing window because, as salient parts of the image, they affect the framing although they are not of interest for the viewer.
  • the automatic reframing method comprises a step of detection of layout areas in the source image in compliance with the automatic layout detection method previously described, these layout areas being then taken into account during the reduced size image generation step.
  • the saliency map generation step for the automatic reframing method is advantageously that of the automatic layout area detection method.
  • the salience values of the points contained in the bounding window(s) determined by the layout area detection method are set to zero.
  • the salience areas produced by the layout areas of the source image are withdrawn or deleted in the saliency map.
  • the saliency map is thus "cleaned”.
  • the size and position of the framing window is then calculated using this "cleaned" saliency map.
  • the automatic determination of the framing window is no longer contaminated by the saliency of layout areas of the source image.
  • the bounding window(s) determined by the layout area detection method are considered as being prohibited areas.
  • the framing window is then determined in such a way as to not comprise pixels corresponding to points that belong to a prohibited area.
  • the reduced size image does not therefore comprise any layout areas detected by the automatic detection method of the invention.
  • a third embodiment consists in combining these two embodiments, in that the saliency map used to determine the position and size of the framing window is not only cleaned but, in addition, the automatic framing window is determined to not contain pixels corresponding to pixels belonging to layout areas.
  • Figure 4B shows the automatic reframing window determined by the method of the invention (third embodiment) to be compared with figure 4A showing the automatic reframing window determined by a standard method in the case of an image showing a scene from a football match.
  • the processed source image shows more particularly players on the football pitch in the lower and middle parts and spectators installed in the stands in the upper part.
  • the match time and score are displayed in the upper left-hand corner of the image and a logo is displayed in the upper right-hand corner of the image.
  • a standard automatic reframing method is applied to this image ( figure 4A )
  • a framing window (white rectangle in the figure) is obtained bounding both the players and the layout areas (that is the match time, the score and the logo).
  • the layout areas are excluded from the window.
  • the window is positioned and dimensioned so as to only comprise the players.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Image Analysis (AREA)
  • Processing Or Creating Images (AREA)
  • Studio Circuits (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
EP09164076.3A 2008-06-30 2009-06-29 Verfahren zur Erkennung von Layoutbereichen in einem Videobild und Verfahren zur Erzeugung eine Bildes reduzierter Grösse welches das Erkennungsverfahren verwendet Active EP2141658B1 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR0854409 2008-06-30

Publications (2)

Publication Number Publication Date
EP2141658A1 true EP2141658A1 (de) 2010-01-06
EP2141658B1 EP2141658B1 (de) 2013-05-01

Family

ID=40344663

Family Applications (1)

Application Number Title Priority Date Filing Date
EP09164076.3A Active EP2141658B1 (de) 2008-06-30 2009-06-29 Verfahren zur Erkennung von Layoutbereichen in einem Videobild und Verfahren zur Erzeugung eine Bildes reduzierter Grösse welches das Erkennungsverfahren verwendet

Country Status (4)

Country Link
EP (1) EP2141658B1 (de)
JP (1) JP5399790B2 (de)
KR (1) KR101678208B1 (de)
CN (1) CN101620731B (de)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101980248A (zh) * 2010-11-09 2011-02-23 西安电子科技大学 基于改进视觉注意力模型的自然场景目标检测方法
WO2012006007A2 (en) * 2010-07-07 2012-01-12 3M Innovative Properties Company Systems and methods for improving visual attention models
EP2709039A1 (de) 2012-09-17 2014-03-19 Thomson Licensing Vorrichtung und Verfahren zur Detektion des Vorhandenseins eines Logos in einem Bild
EP2731074A1 (de) * 2012-11-13 2014-05-14 Thomson Licensing Verfahren zum Reframing eines Bildes basierend auf einer Auffälligkeitskarte
US9478044B2 (en) 2013-03-28 2016-10-25 Thomson Licensing Method and apparatus of creating a perceptual harmony map
US9641795B2 (en) 2011-07-19 2017-05-02 Thomson Licensing Dtv Method and apparatus for reframing and encoding a video signal

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150178587A1 (en) * 2012-06-18 2015-06-25 Thomson Licensing Device and a method for color harmonization of an image
CN109145784B (zh) * 2018-08-03 2022-06-03 百度在线网络技术（北京）有限公司 用于处理视频的方法和装置
CN110992251B (zh) * 2019-11-29 2023-11-10 北京金山云网络技术有限公司 视频中logo替换方法、装置及电子设备

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2006072896A2 (en) * 2005-01-07 2006-07-13 Koninklijke Philips Electronics N.V. Method and electronic device for detecting a graphical object
EP1685288A1 (de) 2003-09-19 2006-08-02 A. Monforts Textilmaschinen GmbH & Co. KG. Düsenblaskasten eines spannrahmens
EP1936566A1 (de) * 2006-12-22 2008-06-25 Thomson Licensing Verfahren zum Erzeugen einer Karte mit den hervorstechenden Merkmalen eines Bildes und System zum Erzeugen von verkleinerten Bildern von Videoframes

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7116716B2 (en) * 2002-11-01 2006-10-03 Microsoft Corporation Systems and methods for generating a motion attention model
CN1904940A (zh) * 2005-07-28 2007-01-31 汤姆森许可贸易公司 用于产生缩减尺寸的图像序列的方法与设备
JP4634894B2 (ja) * 2005-09-05 2011-02-16 パイオニア株式会社 テロップ検出装置及び方法並びにレコーダ

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1685288A1 (de) 2003-09-19 2006-08-02 A. Monforts Textilmaschinen GmbH & Co. KG. Düsenblaskasten eines spannrahmens
WO2006072896A2 (en) * 2005-01-07 2006-07-13 Koninklijke Philips Electronics N.V. Method and electronic device for detecting a graphical object
EP1936566A1 (de) * 2006-12-22 2008-06-25 Thomson Licensing Verfahren zum Erzeugen einer Karte mit den hervorstechenden Merkmalen eines Bildes und System zum Erzeugen von verkleinerten Bildern von Videoframes

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
ITTI L ET AL: "A Principled Approach to Detecting Surprising Events in Video", COMPUTER VISION AND PATTERN RECOGNITION, 2005 IEEE COMPUTER SOCIETY CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, vol. 1, 20 June 2005 (2005-06-20), pages 631 - 637, XP010817332 *
LE MEUR ET AL: "Predicting visual fixations on video based on low-level visual features", VISION RESEARCH, PERGAMON PRESS, OXFORD, GB, vol. 47, no. 19, 1 September 2007 (2007-09-01), pages 2483 - 2498, XP022237937, ISSN: 0042-6989 *
ZYGA K J ET AL: "Logo recognition using retinal coding", SIGNALS, SYSTEMS AND COMPUTERS, 2004. CONFERENCE RECORD OF THE THIRTY- EIGHTH ASILOMAR CONFERENCE ON PACIFIC GROVE, CA, USA NOV. 7-10, 2004, PISCATAWAY, NJ, USA,IEEE, vol. 2, 7 November 2004 (2004-11-07), pages 1549 - 1553, XP010781243 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012006007A2 (en) * 2010-07-07 2012-01-12 3M Innovative Properties Company Systems and methods for improving visual attention models
WO2012006007A3 (en) * 2010-07-07 2012-03-01 3M Innovative Properties Company Systems and methods for improving visual attention models
US10515163B2 (en) 2010-07-07 2019-12-24 3M Innovative Properties Company Systems and methods for improving visual attention models
CN101980248A (zh) * 2010-11-09 2011-02-23 西安电子科技大学 基于改进视觉注意力模型的自然场景目标检测方法
CN101980248B (zh) * 2010-11-09 2012-12-05 西安电子科技大学 基于改进视觉注意力模型的自然场景目标检测方法
US9641795B2 (en) 2011-07-19 2017-05-02 Thomson Licensing Dtv Method and apparatus for reframing and encoding a video signal
EP2709039A1 (de) 2012-09-17 2014-03-19 Thomson Licensing Vorrichtung und Verfahren zur Detektion des Vorhandenseins eines Logos in einem Bild
EP2709038A1 (de) 2012-09-17 2014-03-19 Thomson Licensing Vorrichtung und Verfahren zur Detektion des Vorhandenseins eines Logos in einem Bild
US9311533B2 (en) 2012-09-17 2016-04-12 Thomson Licensing Device and method for detecting the presence of a logo in a picture
EP2731074A1 (de) * 2012-11-13 2014-05-14 Thomson Licensing Verfahren zum Reframing eines Bildes basierend auf einer Auffälligkeitskarte
US9478044B2 (en) 2013-03-28 2016-10-25 Thomson Licensing Method and apparatus of creating a perceptual harmony map

Also Published As

Publication number Publication date
JP5399790B2 (ja) 2014-01-29
CN101620731B (zh) 2013-10-16
KR101678208B1 (ko) 2016-11-21
CN101620731A (zh) 2010-01-06
JP2010033565A (ja) 2010-02-12
EP2141658B1 (de) 2013-05-01
KR20100003233A (ko) 2010-01-07

Similar Documents

Publication Publication Date Title
EP2141658B1 (de) Verfahren zur Erkennung von Layoutbereichen in einem Videobild und Verfahren zur Erzeugung eine Bildes reduzierter Grösse welches das Erkennungsverfahren verwendet
US8374436B2 (en) Method for detecting layout areas in a video image and method for generating an image of reduced size using the detection method
US7027101B1 (en) Selectively overlaying a user interface atop a video signal
US9311533B2 (en) Device and method for detecting the presence of a logo in a picture
US8355079B2 (en) Temporally consistent caption detection on videos using a 3D spatiotemporal method
EP1482731A2 (de) Verfahren und Vorrichtung zur Generierung eines Rundfunkprogramminhaltsmenüs
KR20070120403A (ko) 영상 편집장치 및 방법
WO2020154556A1 (en) Methods and systems for extracting sport-related information from digital video frames
WO2020154554A1 (en) Methods and systems for scoreboard region detection
US20210326626A1 (en) Methods and Systems for Determining Accuracy of Sport-Related Information Extracted from Digital Video Frames
WO2020154555A1 (en) Methods and systems for scoreboard text region detection
EP2017788A1 (de) Abschirmobjekt-videobild-identifizierungseinrichtung und verfahren
WO2020154553A1 (en) Methods and systems for sport data extraction
US9218782B2 (en) Video window detection
KR101193549B1 (ko) 티브이 프로그램의 에피소드 자동분할 시스템 및 그 방법
US20040246259A1 (en) Music program contents menu creation apparatus and method
JPH09181953A (ja) 自動追尾装置
US9883162B2 (en) Stereoscopic image inspection device, stereoscopic image processing device, and stereoscopic image inspection method
Kopf et al. Analysis and retargeting of ball sports video
JP2009093472A (ja) 文字表示領域検出装置及びその方法、並びに携帯端末
JP3144257B2 (ja) 画面サイズ調整装置
AU2015101938A4 (en) Assessment of sporting incidents
JP2001289942A (ja) 自動目標探知装置
KR20150049249A (ko) 스포츠 경기 영상에서의 이벤트 추출 장치 및 이를 이용한 이벤트 추출 방법

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK TR

RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: THOMSON LICENSING

17P Request for examination filed

Effective date: 20100705

17Q First examination report despatched

Effective date: 20100804

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 3/00 20060101ALN20120704BHEP

Ipc: G06K 9/32 20060101ALN20120704BHEP

Ipc: G06T 7/00 20060101AFI20120704BHEP

Ipc: G06K 9/00 20060101ALN20120704BHEP

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

REG Reference to a national code

Ref country code: DE

Ref legal event code: R079

Ref document number: 602009015367

Country of ref document: DE

Free format text: PREVIOUS MAIN CLASS: G06T0007400000

Ipc: G06T0007000000

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAS Grant fee paid

Free format text: ORIGINAL CODE: EPIDOSNIGR3

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

RIC1 Information provided on ipc code assigned before grant

Ipc: G06T 7/00 20060101AFI20130124BHEP

Ipc: G06K 9/00 20060101ALN20130124BHEP

Ipc: G06T 3/00 20060101ALN20130124BHEP

Ipc: G06K 9/32 20060101ALN20130124BHEP

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Kind code of ref document: B1

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO SE SI SK TR

REG Reference to a national code

Ref country code: GB

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: CH

Ref legal event code: EP

Ref country code: AT

Ref legal event code: REF

Ref document number: 610339

Country of ref document: AT

Kind code of ref document: T

Effective date: 20130515

REG Reference to a national code

Ref country code: IE

Ref legal event code: FG4D

REG Reference to a national code

Ref country code: GB

Ref legal event code: 746

Effective date: 20130510

REG Reference to a national code

Ref country code: DE

Ref legal event code: R096

Ref document number: 602009015367

Country of ref document: DE

Effective date: 20130627

REG Reference to a national code

Ref country code: AT

Ref legal event code: MK05

Ref document number: 610339

Country of ref document: AT

Kind code of ref document: T

Effective date: 20130501

REG Reference to a national code

Ref country code: NL

Ref legal event code: VDEP

Effective date: 20130501

REG Reference to a national code

Ref country code: LT

Ref legal event code: MG4D

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: PT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130902

Ref country code: AT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: GR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130802

Ref country code: NO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130801

Ref country code: ES

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130812

Ref country code: SI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: LT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: FI

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: IS

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130901

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BG

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130801

Ref country code: CY

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: HR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: PL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LV

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MC

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: BE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: EE

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: SK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: CZ

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: DK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: RO

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: IT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

REG Reference to a national code

Ref country code: IE

Ref legal event code: MM4A

26N No opposition filed

Effective date: 20140204

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: IE

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130629

Ref country code: CH

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130630

Ref country code: LI

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130630

REG Reference to a national code

Ref country code: DE

Ref legal event code: R097

Ref document number: 602009015367

Country of ref document: DE

Effective date: 20140204

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: MT

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: TR

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: LU

Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES

Effective date: 20130629

Ref country code: MK

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT

Effective date: 20130501

Ref country code: HU

Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO

Effective date: 20090629

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 8

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 9

REG Reference to a national code

Ref country code: DE

Ref legal event code: R082

Ref document number: 602009015367

Country of ref document: DE

Representative=s name: DEHNS, DE

Ref country code: DE

Ref legal event code: R082

Ref document number: 602009015367

Country of ref document: DE

Representative=s name: DEHNS PATENT AND TRADEMARK ATTORNEYS, DE

Ref country code: DE

Ref legal event code: R082

Ref document number: 602009015367

Country of ref document: DE

Representative=s name: HOFSTETTER, SCHURACK & PARTNER PATENT- UND REC, DE

REG Reference to a national code

Ref country code: FR

Ref legal event code: PLFP

Year of fee payment: 10

REG Reference to a national code

Ref country code: FR

Ref legal event code: TP

Owner name: THOMSON LICENSING DTV, FR

Effective date: 20180830

REG Reference to a national code

Ref country code: GB

Ref legal event code: 732E

Free format text: REGISTERED BETWEEN 20180927 AND 20181005

REG Reference to a national code

Ref country code: DE

Ref legal event code: R082

Ref document number: 602009015367

Country of ref document: DE

Representative=s name: DEHNS, DE

Ref country code: DE

Ref legal event code: R081

Ref document number: 602009015367

Country of ref document: DE

Owner name: INTERDIGITAL MADISON PATENT HOLDINGS, FR

Free format text: FORMER OWNER: THOMSON LICENSING, ISSY-LES-MOULINEAUX, FR

Ref country code: DE

Ref legal event code: R082

Ref document number: 602009015367

Country of ref document: DE

Representative=s name: DEHNS PATENT AND TRADEMARK ATTORNEYS, DE

P01 Opt-out of the competence of the unified patent court (upc) registered

Effective date: 20230514

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 20230622

Year of fee payment: 15

Ref country code: DE

Payment date: 20230627

Year of fee payment: 15

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 20230620

Year of fee payment: 15